v2.7.1

2.7.1 (2026-03-18)

Bug Fixes

• rules: correct KG#156 -- CI validator only checks See-Also lines, not all text (#420) (d61b209)

v2.7.0

2.7.0 (2026-03-17)

Features

• add samverk-checkout skill for MCP work protocol (#400) (#406) (b3e268e)

v2.6.0

2.6.0 (2026-03-17)

Features

• add Samverk MCP routing + fix KG#152 scope + [MCP-TOOLS] checklist (#396) (62aeace)
• add samverk-dispatch skill for dispatcher work protocol (#398) (d2732ff)

Bug Fixes

• errcheck file handles in GO-CI checklist + MCP hang prevention (#391) (4cb8b13)

v2.5.0

2.5.0 (2026-03-17)

Features

• add archive recovery workflow and Synapset conformance check (#379) (96b5956)
• add synapset skill with structured retrieval guide (#356) (1c3be95)
• autolearn: ingest #330 + update status.md (#332) (daade3c)
• autolearn: ingest #343 (SQLite PRAGMA + Gitea assign gotchas) (#347) (ac4c5f8)
• autolearn: ingest #348 + #349 (Ollama gotchas) (#351) (19d2915)
• autolearn: ingest #354 (trivy cleanup + Gitea merge API) (#355) (25c8e66)
• autolearn: ingest 15 issues as rules entries (#309-#328) (#329) (dab9c64)
• autolearn: sync batch-ingested entries to Synapset pool (#333) (#339) (5c784e3)
• hooks: add commit/push verification reminder hook (#369) (e05e2c7)
• hooks: add pre-commit and commit-msg git hook templates (#366) (919fe75)
• hooks: add SessionStop hook for session-end hygiene (#365) (16e7115)
• hooks: add SubagentStop verification hook (#368) (1b75c04)
• metrics: add conformance score persistence and autolearn velocity (#336) (#341) (18d6eb4)
• metrics: add effectiveness measurement skill and data model (#334) (#338) (5b99d1e)
• metrics: add visual HTML dashboard generator (#346) (3a058f7)
• metrics: add weekly PR metrics collection GH Action (#337) (#342) (1b51616)
• metrics: enhance dashboard with unified theme (#350) (#352) (ad80efa)
• metrics: session instrumentation and pattern tracking (#340) (c5981dd)
• metrics: track Synapset pattern applications across all projects (#345) (2554388)
• Synapset-backed compaction architecture (#376) (ae2948a)

Bug Fixes

• collect-pr-metrics.sh Python fallback for MSYS/Windows (#344) (39e32f2)
• docs: correct pattern counts and skill list drift (#353) (5888070)
• docs: correct pattern counts and status drift (#359) (b39018a)
• rules: correct KG#135 -- OAuth not required for Custom Connectors (#357) (113e5a2)
• sync release-please manifest to v2.4.0 (#382) (29520df)

v2.3.0 -- Rules Compaction, Synapset Integration & MCP Research

Highlights

• Rules compaction: AP 42k->35k, KG 50k->30k (30% combined reduction) -- archives stale entries, consolidates related patterns, improves session performance
• Synapset integration: Semantic vector memory backend for autolearn -- dual-store to MCP Memory + Synapset, [SYNAPSET] checklist block for pre-task pattern search
• MCP lazy-loading research: Feasibility assessment for custom gateway -- verdict: wait (ToolSearch provides ~85% context reduction). Feature request filed: anthropics/claude-code#34471
• 16 new patterns: Worktree isolation, go:embed cache, Tailscale Funnel, Cloudflare Email Routing, sqlite-vec dimensions, and more
• Tool selection guide: New rules file for proactive tool routing decisions
• Cross-reference verification: /rules-compact Step 8 prevents stale AP/KG cross-references after archiving

Stats

• 8 PRs merged, 15 issues closed
• 11 rules files, 150 patterns (AP: 74, KG: 76)
• 21 skills, 7 agents
• 71 stale branches cleaned

Full changelog: CHANGELOG.md

v2.2.0 -- Rule Lifecycle Management

Rule lifecycle management for the autolearn system.

Added

• Rule lifecycle metadata format (ADR-0014): Per-entry metadata (**Added:**, **Source:**, **Status:**, **Last relevant:**, **See also:**), deprecation states, and archive strategy
• Archive directory: claude/rules/archive/ for deprecated entries (not loaded into sessions)
• Metadata PoC: 10 entries annotated, AP#27/KG#17 duplicate resolved, swagger cluster cross-referenced
• Rules audit workflow: /reflect option 5 for health check and maintenance
• Last-relevant tracking: /reflect updates timestamps on entries applied during sessions

Changed

• Autolearn-patterns entry count: 76 -> 75 (AP#27 archived as superseded by KG#17)

See CHANGELOG.md for full details.

v2.1.0 -- Governance & Quality Gates

Governance and quality gates for the autolearn system.

Added

• Tiered rule governance: core-principles.md (Tier 0, immutable) and error-policy.md (Tier 1, governed) with YAML frontmatter tier metadata
• SessionStart health checks: symlink integrity verification and CLAUDE.md detection at session start
• Pre-commit verification: build/test/lint gates before commit in workflow preferences
• Fix-forward workflow: zero-tolerance error policy replacing "pre-existing" classification
• Template quality gates: CI scaffolding templates include lint and test verification steps
• Autolearn scope-aware routing: in DevKit write Tier 2 rules directly; in projects write to MCP Memory and create DevKit issues
• Rule validation pipeline: five-stage gate for proposed rules (dangerous pattern scan, core principles check, conflict check, risk classification, storage decision)
• Propagation verification: /devkit-sync verify checks all active projects for DevKit update propagation; SessionStart reports rule file changes
• /devkit-sync promote and /devkit-sync update subcommands

Changed

• Autolearn workflows now include validation and scope assessment steps
• update-knowledge.md requires DevKit context (context guard)
• Rules file count: 8 → 10

Full Changelog: v2.0.0...v2.1.0